industry-mar11Top10 / topics.json
Thang203's picture
Add BERTopic model
476ef25 verified
{
"topic_representations": {
"-1": [
[
"models",
0.036874579738434304
],
[
"language",
0.031011734360675242
],
[
"data",
0.02740357251248468
],
[
"large",
0.024331696551107916
],
[
"language models",
0.02287739800299974
],
[
"model",
0.02123690372233833
],
[
"tasks",
0.02117889409597425
],
[
"llms",
0.020210440809796944
],
[
"large language",
0.019999417196753248
],
[
"large language models",
0.019126572684958956
]
],
"0": [
[
"models",
0.03888243759552385
],
[
"model",
0.03647492283412293
],
[
"language",
0.03613590283186468
],
[
"training",
0.025581428828302905
],
[
"language models",
0.02386262298037925
],
[
"tasks",
0.02360941221543806
],
[
"data",
0.021604280018978572
],
[
"performance",
0.021213047327713713
],
[
"large",
0.020365016161611835
],
[
"method",
0.01788214168631935
]
],
"1": [
[
"code",
0.08112439886630912
],
[
"language",
0.03515934823155083
],
[
"models",
0.034093014905089085
],
[
"llms",
0.03351276274167474
],
[
"programming",
0.03221809114638236
],
[
"software",
0.024215765671622126
],
[
"language models",
0.023501871498181743
],
[
"tasks",
0.021362088649701006
],
[
"model",
0.021028623583260922
],
[
"large language",
0.020242713470511334
]
],
"2": [
[
"ai",
0.03748085558879784
],
[
"models",
0.032123956517937674
],
[
"language",
0.030708509906927736
],
[
"dialogue",
0.02863305325688509
],
[
"human",
0.027796744355540557
],
[
"llms",
0.027095383693882993
],
[
"chatgpt",
0.02427426857972807
],
[
"large language",
0.024177158942537805
],
[
"large",
0.023491817699557018
],
[
"model",
0.022240448993628016
]
],
"3": [
[
"detection",
0.04600933370915614
],
[
"models",
0.0376182869533305
],
[
"text",
0.03622151327830574
],
[
"language",
0.03555056937300613
],
[
"model",
0.02910562167494557
],
[
"large",
0.026737322113278325
],
[
"language models",
0.026260255642963005
],
[
"misinformation",
0.022438367434259674
],
[
"dataset",
0.021178404179731523
],
[
"large language",
0.020266242724238725
]
],
"4": [
[
"multimodal",
0.06377037276103617
],
[
"visual",
0.0609342279209814
],
[
"image",
0.05031813021481461
],
[
"models",
0.04428945209100523
],
[
"generation",
0.03866971167435956
],
[
"video",
0.03452530411071284
],
[
"understanding",
0.03174883479055843
],
[
"large",
0.02994331997174661
],
[
"model",
0.027842071361726516
],
[
"instruction",
0.02744625284444433
]
],
"5": [
[
"agents",
0.032621488861863626
],
[
"language",
0.032046686285534975
],
[
"policy",
0.031585563861493055
],
[
"learning",
0.030550747755560888
],
[
"tasks",
0.029270078392980483
],
[
"llms",
0.028067175067745524
],
[
"agent",
0.026011640827111927
],
[
"games",
0.025255064827310037
],
[
"knowledge",
0.02496878818528055
],
[
"model",
0.024630611822384848
]
],
"6": [
[
"speech",
0.12032183461065618
],
[
"asr",
0.0784134014691984
],
[
"text",
0.04816267150192302
],
[
"speaker",
0.04549115752552982
],
[
"recognition",
0.044013060675693126
],
[
"speech recognition",
0.03480823666083872
],
[
"model",
0.0329226249448169
],
[
"language",
0.031171151406766243
],
[
"voice",
0.030863819919231247
],
[
"proposed",
0.029531042059903895
]
],
"7": [
[
"reasoning",
0.09733768593924219
],
[
"cot",
0.04159609177483568
],
[
"models",
0.04032110830244759
],
[
"problems",
0.038531107231743966
],
[
"commonsense",
0.0328390198222387
],
[
"language",
0.03061562593615061
],
[
"prompting",
0.03050017742462947
],
[
"language models",
0.028282815332533393
],
[
"math",
0.026470858073982147
],
[
"chainofthought",
0.026470858073982147
]
],
"8": [
[
"retrieval",
0.05391749257643426
],
[
"information",
0.041311727463775545
],
[
"query",
0.03998637165786005
],
[
"llms",
0.0360048263616992
],
[
"models",
0.03235786882267994
],
[
"language",
0.03201012649638935
],
[
"queries",
0.031828706522162444
],
[
"language models",
0.02804152194835136
],
[
"large",
0.026588466396316807
],
[
"knowledge",
0.02430262486413176
]
]
},
"topics": [
0,
3,
6,
-1,
0,
-1,
0,
0,
-1,
0,
0,
-1,
0,
0,
1,
-1,
0,
-1,
-1,
7,
-1,
0,
0,
-1,
0,
8,
0,
-1,
-1,
2,
2,
8,
0,
2,
0,
0,
5,
8,
0,
0,
0,
0,
0,
0,
2,
-1,
3,
2,
3,
0,
6,
-1,
3,
-1,
2,
0,
0,
-1,
1,
0,
3,
1,
0,
1,
0,
0,
0,
2,
0,
0,
0,
-1,
-1,
6,
-1,
-1,
2,
3,
0,
0,
0,
2,
0,
7,
0,
-1,
6,
3,
2,
-1,
-1,
0,
0,
-1,
3,
0,
4,
0,
1,
3,
0,
0,
0,
1,
0,
7,
2,
-1,
6,
5,
-1,
-1,
0,
0,
-1,
0,
2,
-1,
0,
0,
7,
0,
-1,
3,
1,
-1,
-1,
3,
5,
7,
6,
8,
0,
5,
1,
1,
1,
1,
5,
0,
-1,
-1,
5,
3,
3,
-1,
-1,
5,
1,
3,
0,
-1,
-1,
0,
0,
0,
7,
-1,
3,
7,
0,
-1,
6,
8,
-1,
0,
-1,
0,
0,
-1,
7,
0,
1,
4,
0,
7,
0,
-1,
1,
-1,
2,
-1,
0,
-1,
-1,
2,
0,
-1,
0,
-1,
0,
-1,
2,
-1,
-1,
3,
8,
3,
6,
-1,
-1,
2,
4,
0,
6,
-1,
4,
-1,
7,
2,
4,
-1,
8,
-1,
0,
0,
4,
0,
2,
2,
-1,
3,
-1,
-1,
-1,
-1,
8,
-1,
0,
4,
-1,
-1,
1,
1,
1,
8,
0,
1,
2,
-1,
1,
-1,
2,
2,
-1,
4,
2,
-1,
0,
6,
-1,
4,
-1,
-1,
-1,
7,
-1,
-1,
0,
-1,
1,
-1,
0,
-1,
0,
-1,
2,
1,
2,
0,
-1,
-1,
-1,
2,
0,
2,
-1,
8,
7,
0,
1,
5,
-1,
-1,
-1,
0,
2,
0,
-1,
0,
-1,
-1,
-1,
3,
2,
-1,
7,
-1,
0,
0,
-1,
-1,
1,
-1,
-1,
0,
1,
3,
7,
1,
-1,
0,
-1,
0,
-1,
-1,
0,
-1,
-1,
0,
5,
-1,
1,
0,
1,
8,
0,
2,
1,
-1,
1,
5,
0,
-1,
4,
1,
1,
0,
-1,
-1,
2,
4,
-1,
0,
0,
-1,
2,
0,
-1,
2,
1,
5,
3,
6,
5,
2,
1,
4,
5,
-1,
-1,
2,
-1,
6,
0,
2,
-1,
-1,
-1,
3,
4,
4,
-1,
1,
-1,
6,
-1,
-1,
1,
-1,
5,
-1,
4,
1,
4,
-1,
0,
0,
-1,
-1,
6,
5,
2,
-1,
-1,
-1,
-1,
-1,
-1,
4,
-1,
-1,
-1,
-1,
5,
-1,
-1,
0,
-1,
2,
3,
1,
2,
-1,
1,
7,
-1,
4,
-1,
1,
3,
-1,
8,
0,
1,
-1,
0,
1,
0,
4,
8,
-1,
3,
-1,
4,
4,
2,
5,
8,
3,
7,
3,
0,
1,
8,
-1,
6,
4,
0,
7,
-1,
6,
4,
-1,
6,
-1,
0,
-1,
-1,
7,
1,
3,
-1,
0,
6,
-1,
1,
2,
3,
2,
1,
5,
0,
-1,
6,
-1,
0,
0,
1,
6,
5,
-1,
0,
2,
-1,
-1,
0,
3,
0,
2,
3,
2,
2,
7,
1,
-1,
1,
1,
-1,
3,
-1,
6,
0,
4,
0,
5,
-1,
-1,
-1,
-1,
5,
5,
-1,
2,
-1,
-1
],
"topic_sizes": {
"0": 118,
"3": 32,
"6": 21,
"-1": 169,
"1": 49,
"7": 19,
"8": 15,
"2": 47,
"5": 22,
"4": 24
},
"topic_mapper": [
[
-1,
-1,
-1,
-1
],
[
0,
0,
7,
4
],
[
1,
1,
4,
6
],
[
2,
2,
8,
3
],
[
3,
3,
5,
1
],
[
4,
4,
6,
5
],
[
5,
5,
3,
7
],
[
6,
6,
1,
8
],
[
7,
7,
2,
2
],
[
8,
8,
0,
0
],
[
9,
9,
0,
0
],
[
10,
10,
0,
0
]
],
"topic_labels": {
"-1": "-1_models_language_data_large",
"0": "0_models_model_language_training",
"1": "1_code_language_models_llms",
"2": "2_ai_models_language_dialogue",
"3": "3_detection_models_text_language",
"4": "4_multimodal_visual_image_models",
"5": "5_agents_language_policy_learning",
"6": "6_speech_asr_text_speaker",
"7": "7_reasoning_cot_models_problems",
"8": "8_retrieval_information_query_llms"
},
"custom_labels": null,
"_outliers": 1,
"topic_aspects": {
"KeyBERT": {
"-1": [
[
"large language models",
0.6703740358352661
],
[
"large language models llms",
0.6190640330314636
],
[
"language models",
0.6147422790527344
],
[
"language models llms",
0.567597508430481
],
[
"language model",
0.5490379333496094
],
[
"large language",
0.47846218943595886
],
[
"natural language",
0.47019103169441223
],
[
"language",
0.36398622393608093
],
[
"training data",
0.36353152990341187
],
[
"models",
0.3585664629936218
]
],
"0": [
[
"large language models",
0.651195228099823
],
[
"pretrained language",
0.512614905834198
],
[
"language models",
0.49944019317626953
],
[
"large language",
0.49680691957473755
],
[
"language model",
0.44212523102760315
],
[
"machine translation",
0.3898525834083557
],
[
"sparse",
0.3684082329273224
],
[
"memory",
0.35640034079551697
],
[
"corpus",
0.3460950255393982
],
[
"attention",
0.34196916222572327
]
],
"1": [
[
"code generation",
0.5884341597557068
],
[
"code completion",
0.5430147647857666
],
[
"source code",
0.5036313533782959
],
[
"large language models",
0.4955924153327942
],
[
"large language models llms",
0.48612886667251587
],
[
"language models",
0.44613733887672424
],
[
"software engineering",
0.44518738985061646
],
[
"language models llms",
0.44061607122421265
],
[
"programming",
0.41835474967956543
],
[
"coding",
0.4044494926929474
]
],
"2": [
[
"large language models",
0.6216679215431213
],
[
"conversational ai",
0.6001573204994202
],
[
"large language models llms",
0.588668167591095
],
[
"language models",
0.5686337351799011
],
[
"chatbots",
0.5604218244552612
],
[
"language models llms",
0.5467207431793213
],
[
"language model",
0.5185490250587463
],
[
"large language",
0.5117849111557007
],
[
"natural language",
0.4800942540168762
],
[
"dialogues",
0.437444806098938
]
],
"3": [
[
"large language models",
0.5753244161605835
],
[
"large language models llms",
0.5593785047531128
],
[
"language models",
0.5217305421829224
],
[
"language models llms",
0.5088766813278198
],
[
"machinegenerated text",
0.49884361028671265
],
[
"language model",
0.45426321029663086
],
[
"large language",
0.4042874574661255
],
[
"texts",
0.3673853576183319
],
[
"classifier",
0.354655921459198
],
[
"text",
0.3459568917751312
]
],
"4": [
[
"multimodal large language",
0.6466671228408813
],
[
"multimodal models",
0.63934326171875
],
[
"multimodal",
0.6179039478302002
],
[
"multimodal large",
0.5376994609832764
],
[
"visual",
0.47933536767959595
],
[
"large language models",
0.4537416696548462
],
[
"visionlanguage",
0.4349161982536316
],
[
"language models",
0.42795825004577637
],
[
"large language model",
0.4277690649032593
],
[
"visual foundation models",
0.40677300095558167
]
],
"5": [
[
"large language models llms",
0.4626759886741638
],
[
"ai",
0.4613281488418579
],
[
"language models llms",
0.45701661705970764
],
[
"agent",
0.4489193260669708
],
[
"large language models",
0.4476342499256134
],
[
"agents",
0.44667837023735046
],
[
"interactive",
0.439677357673645
],
[
"language models",
0.4368625581264496
],
[
"reinforcement",
0.4350704550743103
],
[
"language model",
0.42887791991233826
]
],
"6": [
[
"automatic speech",
0.6606317758560181
],
[
"automatic speech recognition asr",
0.5792312622070312
],
[
"speech recognition",
0.5414796471595764
],
[
"speech recognition asr",
0.5414656400680542
],
[
"automatic speech recognition",
0.5386157035827637
],
[
"large language models",
0.529854416847229
],
[
"large language model",
0.5051016211509705
],
[
"utterances",
0.49932384490966797
],
[
"language models",
0.46869075298309326
],
[
"voice",
0.43832945823669434
]
],
"7": [
[
"reasoning large language models",
0.69033282995224
],
[
"reasoning tasks",
0.6320525407791138
],
[
"reasoning large language",
0.630852460861206
],
[
"reasoning capabilities",
0.6158041954040527
],
[
"reasoning benchmarks",
0.5364079475402832
],
[
"large language models",
0.48382115364074707
],
[
"large language models llms",
0.4739667773246765
],
[
"complex reasoning",
0.46622762084007263
],
[
"language models",
0.46207302808761597
],
[
"language models llms",
0.453142374753952
]
],
"8": [
[
"large language models llm",
0.6180689334869385
],
[
"large language models llms",
0.6018953323364258
],
[
"large language models",
0.5865136384963989
],
[
"language models llm",
0.5565090179443359
],
[
"language models llms",
0.5427590608596802
],
[
"language models",
0.5051120519638062
],
[
"information retrieval",
0.5001324415206909
],
[
"retrieval",
0.46649327874183655
],
[
"knowledge bases",
0.4627561569213867
],
[
"large language",
0.3926961421966553
]
]
},
"MMR": {
"-1": [
[
"models",
0.036874579738434304
],
[
"language",
0.031011734360675242
],
[
"data",
0.02740357251248468
],
[
"large",
0.024331696551107916
],
[
"language models",
0.02287739800299974
],
[
"model",
0.02123690372233833
],
[
"tasks",
0.02117889409597425
],
[
"llms",
0.020210440809796944
],
[
"large language",
0.019999417196753248
],
[
"large language models",
0.019126572684958956
]
],
"0": [
[
"models",
0.03888243759552385
],
[
"model",
0.03647492283412293
],
[
"language",
0.03613590283186468
],
[
"training",
0.025581428828302905
],
[
"language models",
0.02386262298037925
],
[
"tasks",
0.02360941221543806
],
[
"data",
0.021604280018978572
],
[
"performance",
0.021213047327713713
],
[
"large",
0.020365016161611835
],
[
"method",
0.01788214168631935
]
],
"1": [
[
"code",
0.08112439886630912
],
[
"language",
0.03515934823155083
],
[
"models",
0.034093014905089085
],
[
"llms",
0.03351276274167474
],
[
"programming",
0.03221809114638236
],
[
"software",
0.024215765671622126
],
[
"language models",
0.023501871498181743
],
[
"tasks",
0.021362088649701006
],
[
"model",
0.021028623583260922
],
[
"large language",
0.020242713470511334
]
],
"2": [
[
"ai",
0.03748085558879784
],
[
"models",
0.032123956517937674
],
[
"language",
0.030708509906927736
],
[
"dialogue",
0.02863305325688509
],
[
"human",
0.027796744355540557
],
[
"llms",
0.027095383693882993
],
[
"chatgpt",
0.02427426857972807
],
[
"large language",
0.024177158942537805
],
[
"large",
0.023491817699557018
],
[
"model",
0.022240448993628016
]
],
"3": [
[
"detection",
0.04600933370915614
],
[
"models",
0.0376182869533305
],
[
"text",
0.03622151327830574
],
[
"language",
0.03555056937300613
],
[
"model",
0.02910562167494557
],
[
"large",
0.026737322113278325
],
[
"language models",
0.026260255642963005
],
[
"misinformation",
0.022438367434259674
],
[
"dataset",
0.021178404179731523
],
[
"large language",
0.020266242724238725
]
],
"4": [
[
"multimodal",
0.06377037276103617
],
[
"visual",
0.0609342279209814
],
[
"image",
0.05031813021481461
],
[
"models",
0.04428945209100523
],
[
"generation",
0.03866971167435956
],
[
"video",
0.03452530411071284
],
[
"understanding",
0.03174883479055843
],
[
"large",
0.02994331997174661
],
[
"model",
0.027842071361726516
],
[
"instruction",
0.02744625284444433
]
],
"5": [
[
"agents",
0.032621488861863626
],
[
"language",
0.032046686285534975
],
[
"policy",
0.031585563861493055
],
[
"learning",
0.030550747755560888
],
[
"tasks",
0.029270078392980483
],
[
"llms",
0.028067175067745524
],
[
"agent",
0.026011640827111927
],
[
"games",
0.025255064827310037
],
[
"knowledge",
0.02496878818528055
],
[
"model",
0.024630611822384848
]
],
"6": [
[
"speech",
0.12032183461065618
],
[
"asr",
0.0784134014691984
],
[
"text",
0.04816267150192302
],
[
"speaker",
0.04549115752552982
],
[
"recognition",
0.044013060675693126
],
[
"speech recognition",
0.03480823666083872
],
[
"model",
0.0329226249448169
],
[
"language",
0.031171151406766243
],
[
"voice",
0.030863819919231247
],
[
"proposed",
0.029531042059903895
]
],
"7": [
[
"reasoning",
0.09733768593924219
],
[
"cot",
0.04159609177483568
],
[
"models",
0.04032110830244759
],
[
"problems",
0.038531107231743966
],
[
"commonsense",
0.0328390198222387
],
[
"language",
0.03061562593615061
],
[
"prompting",
0.03050017742462947
],
[
"language models",
0.028282815332533393
],
[
"math",
0.026470858073982147
],
[
"chainofthought",
0.026470858073982147
]
],
"8": [
[
"retrieval",
0.05391749257643426
],
[
"information",
0.041311727463775545
],
[
"query",
0.03998637165786005
],
[
"llms",
0.0360048263616992
],
[
"models",
0.03235786882267994
],
[
"language",
0.03201012649638935
],
[
"queries",
0.031828706522162444
],
[
"language models",
0.02804152194835136
],
[
"large",
0.026588466396316807
],
[
"knowledge",
0.02430262486413176
]
]
},
"POS": {
"-1": [
[
"models",
0.036874579738434304
],
[
"language",
0.031011734360675242
],
[
"data",
0.02740357251248468
],
[
"large",
0.024331696551107916
],
[
"model",
0.02123690372233833
],
[
"tasks",
0.02117889409597425
],
[
"large language",
0.019999417196753248
],
[
"learning",
0.017245729294018734
],
[
"knowledge",
0.015578401017865536
],
[
"performance",
0.015293299507868716
]
],
"0": [
[
"models",
0.03888243759552385
],
[
"model",
0.03647492283412293
],
[
"language",
0.03613590283186468
],
[
"training",
0.025581428828302905
],
[
"tasks",
0.02360941221543806
],
[
"data",
0.021604280018978572
],
[
"performance",
0.021213047327713713
],
[
"large",
0.020365016161611835
],
[
"method",
0.01788214168631935
],
[
"translation",
0.015317468043852814
]
],
"1": [
[
"code",
0.08112439886630912
],
[
"language",
0.03515934823155083
],
[
"models",
0.034093014905089085
],
[
"programming",
0.03221809114638236
],
[
"software",
0.024215765671622126
],
[
"tasks",
0.021362088649701006
],
[
"model",
0.021028623583260922
],
[
"large language",
0.020242713470511334
],
[
"large",
0.01969750985041782
],
[
"program",
0.017892959453975895
]
],
"2": [
[
"models",
0.032123956517937674
],
[
"language",
0.030708509906927736
],
[
"dialogue",
0.02863305325688509
],
[
"human",
0.027796744355540557
],
[
"large language",
0.024177158942537805
],
[
"large",
0.023491817699557018
],
[
"model",
0.022240448993628016
],
[
"chatbots",
0.021090782635767247
],
[
"responses",
0.020358247264396636
],
[
"agents",
0.019356726824660043
]
],
"3": [
[
"detection",
0.04600933370915614
],
[
"models",
0.0376182869533305
],
[
"text",
0.03622151327830574
],
[
"language",
0.03555056937300613
],
[
"model",
0.02910562167494557
],
[
"large",
0.026737322113278325
],
[
"misinformation",
0.022438367434259674
],
[
"dataset",
0.021178404179731523
],
[
"large language",
0.020266242724238725
],
[
"bias",
0.019222454111824376
]
],
"4": [
[
"multimodal",
0.06377037276103617
],
[
"visual",
0.0609342279209814
],
[
"image",
0.05031813021481461
],
[
"models",
0.04428945209100523
],
[
"generation",
0.03866971167435956
],
[
"video",
0.03452530411071284
],
[
"understanding",
0.03174883479055843
],
[
"large",
0.02994331997174661
],
[
"model",
0.027842071361726516
],
[
"instruction",
0.02744625284444433
]
],
"5": [
[
"agents",
0.032621488861863626
],
[
"language",
0.032046686285534975
],
[
"policy",
0.031585563861493055
],
[
"learning",
0.030550747755560888
],
[
"tasks",
0.029270078392980483
],
[
"agent",
0.026011640827111927
],
[
"games",
0.025255064827310037
],
[
"knowledge",
0.02496878818528055
],
[
"model",
0.024630611822384848
],
[
"models",
0.02357361082959911
]
],
"6": [
[
"speech",
0.12032183461065618
],
[
"text",
0.04816267150192302
],
[
"speaker",
0.04549115752552982
],
[
"recognition",
0.044013060675693126
],
[
"model",
0.0329226249448169
],
[
"language",
0.031171151406766243
],
[
"voice",
0.030863819919231247
],
[
"systems",
0.02868879719738342
],
[
"error",
0.027433755186485595
],
[
"prompt",
0.027359560787395366
]
],
"7": [
[
"reasoning",
0.09733768593924219
],
[
"models",
0.04032110830244759
],
[
"problems",
0.038531107231743966
],
[
"commonsense",
0.0328390198222387
],
[
"language",
0.03061562593615061
],
[
"prompting",
0.03050017742462947
],
[
"math",
0.026470858073982147
],
[
"model",
0.02522199037356587
],
[
"performance",
0.025100359151578013
],
[
"large",
0.024219197113476695
]
],
"8": [
[
"retrieval",
0.05391749257643426
],
[
"information",
0.041311727463775545
],
[
"query",
0.03998637165786005
],
[
"models",
0.03235786882267994
],
[
"language",
0.03201012649638935
],
[
"queries",
0.031828706522162444
],
[
"large",
0.026588466396316807
],
[
"knowledge",
0.02430262486413176
],
[
"augmentation",
0.022439589434192657
],
[
"results",
0.021446519611670142
]
]
}
}
}